33
Click to edit the title text format An Introduction to TuTalk: Developing Dialogue Agents for Learning Applications Pamela Jordan University of Pittsburgh Learning Research and Development Center

An Introduction to TuTalk: Developing Dialogue Agents for Learning Applications

Embed Size (px)

DESCRIPTION

An Introduction to TuTalk: Developing Dialogue Agents for Learning Applications. Pamela Jordan University of Pittsburgh Learning Research and Development Center. Dialogues in Learning Applications. Language practice Peer collaborations Short answer tutorial dialogue AutoTutor - PowerPoint PPT Presentation

Citation preview

Page 1: An Introduction to TuTalk: Developing Dialogue Agents for Learning Applications

Click to edit the title text format

An Introduction to TuTalk: Developing Dialogue Agents for Learning Applications

Pamela Jordan

University of Pittsburgh

Learning Research and Development Center

Page 2: An Introduction to TuTalk: Developing Dialogue Agents for Learning Applications

Dialogues in Learning Applications

Language practice Peer collaborations Short answer tutorial dialogue

AutoTutorCircsim-TutorTuTalk

Page 3: An Introduction to TuTalk: Developing Dialogue Agents for Learning Applications

AutoTutor - Physics

Page 4: An Introduction to TuTalk: Developing Dialogue Agents for Learning Applications

Circsim-Tutor

Page 5: An Introduction to TuTalk: Developing Dialogue Agents for Learning Applications

Cordillera (built using TuTalk)

Page 6: An Introduction to TuTalk: Developing Dialogue Agents for Learning Applications

ProPL (built using TuTalk)

Page 7: An Introduction to TuTalk: Developing Dialogue Agents for Learning Applications

What is TuTalk?

Dialogue system construction tools for learning applicationsAuthoring tools for creating, testing and

maintaining an artificial dialogue partner/agentDialogue system & server that:

Conducts dialogues with multiple students Provides communication protocol for integrating

with interfaces and applications (Several how-to examples provided)

Provides experiment management tools

Page 8: An Introduction to TuTalk: Developing Dialogue Agents for Learning Applications

Finite state dialogue management

As a runner pushes a ball away, what horizontal forces act on it?

{runner’s}{gravitational, *}

<subdialog > <subdialog>Good!

After the push ends, what forces….?

<anything else>

Page 9: An Introduction to TuTalk: Developing Dialogue Agents for Learning Applications

Example dialogue

T: Let’s consider the forces acting on objects after they have been thrown. As a runner pushes a ball away, what horizontal forces are acting on it while she is pushing it?

S: Gravity?T: In what direction does gravity act?S: downwardT: Yes. So is a downward force a horizontal or vertical

force?S: It is verticalT: Right. I asked for the horizontal forces instead and the

only one is from the runner. After the push ends, what horizontal forces are acting

on the ball?

Subdialogue

Page 10: An Introduction to TuTalk: Developing Dialogue Agents for Learning Applications

TuTalk Dialogue System Usage History

Experiment or System Name Domain Number of experiments

Andes-Atlas Quantitative physics 3

Why2-Atlas Qualitative physics 3

ITSpoke Qualitative physics 4

Reflective follow-up Quantitative physics 2

ProPL Computer Science 1

CycleTalk Thermodynamics 2

Collaborative problem solving Math (6th grade) 1

Cordillera Quantitative & qualitative physics 2

18

Page 11: An Introduction to TuTalk: Developing Dialogue Agents for Learning Applications

What do you have to do to create a TuTalk dialogue agent?

Write domain content in form of natural language dialogue turns (e.g. elicit or tell) Write an ideal dialogue on a topic

Write expected short answer student responses (correct, not correct)

Write subdialogues for expected student responses that are:Partially correct/incompletePartially incorrectOverly vagueOverly specificCorrect but premature

Page 12: An Introduction to TuTalk: Developing Dialogue Agents for Learning Applications

Click to edit the title text formatAuthoring, Previewing and Testing Demo

Page 13: An Introduction to TuTalk: Developing Dialogue Agents for Learning Applications

Click to edit the title text formatAuthoring, Previewing and Testing Demo

Page 14: An Introduction to TuTalk: Developing Dialogue Agents for Learning Applications

When are short answer dialogues appropriate/inappropriate?

Appropriate for: practicing some dialogue skills conceptual discussions scaffolding problem solving identifying & addressing gaps in student

understanding only as needed (hints, examples) Not appropriate for:

assessing deep understanding addressing grammar problems in language content delivery – printed text is more efficient student-only initiative (use CTAT instead)

Page 15: An Introduction to TuTalk: Developing Dialogue Agents for Learning Applications

Past Summer School TuTalk projects

Language tutoring:Coaching military trainees to follow one

required communications protocolGiving ESL learners dialogue practiceCoaching student is proper use of two

Chinese lexical items that depend on context

Page 16: An Introduction to TuTalk: Developing Dialogue Agents for Learning Applications

Using TuTalk to build a tutor for

Chinese pronunciation

Wenyan Zhou, Vanderbilt University

Tiffany Taylor, George Mason University

Page 17: An Introduction to TuTalk: Developing Dialogue Agents for Learning Applications

Choosing the wrong pinyin provides feedback and choosing the “right” pinyin but the wrong tone leads to remediation

Page 18: An Introduction to TuTalk: Developing Dialogue Agents for Learning Applications

Past Summer School TuTalk projects

Conceptual tutoring:Coaching elementary school students in

qualitative reasoning skillsCoaching students on loop constructs in

programmingCoaching students in the solution of

monomialsCoaching students on Pythagorean Theorem

Page 19: An Introduction to TuTalk: Developing Dialogue Agents for Learning Applications

CT Percent Tutor + Metacognitive TuTalk Prompts

Primary school aged students Learning Objectives

Learning fractions, percentages, and ratios Translating word problem into an equation

ITS Roles CT

Model Tracing Facilitates problem steps Detect a suboptimal & two buggy paths

TuTalk Metacognitive prompts

Encourages self-monitoring & goal settings Facilitates analogous solution strategies

Dr. Baba Kofi Weusijanae-mail: [email protected]

Yvette Aquie-mail: [email protected]

Page 20: An Introduction to TuTalk: Developing Dialogue Agents for Learning Applications

Demo – CTAT Incorrect Path 1:Percent Conversion Incorrect 2

Page 21: An Introduction to TuTalk: Developing Dialogue Agents for Learning Applications

Demo – TuTalk Script 1 , Example 1

Page 22: An Introduction to TuTalk: Developing Dialogue Agents for Learning Applications

Tuesday TuTalk Track

Track Lecture: Basics of Authoring TuTalk Dialogue Agents Review and expand on basic authoring with GUI Introduce alternative scripting language for authoring

Hands-on: Create a simple TuTalk Dialogue Agent Do section 3.3 of TuTalk Authoring Interface User’s Guide (can do sections

3.1 and 3.2 first if you prefer) Project: Locate relevant dialogues or collect small sample of dialogues

(available corpora http://andes3.lrdc.pitt.edu/TuTalk/corpora/) Track Lecture: The Methodology of Authoring Dialogues

Dialogue authoring methodologies   Advice/findings on effective learning dialogues

Project: Identify problem solving goals to cover in dialogue Project: Begin dialogue authoring (mainlines of reasoning w/ correct

and default follow-up) Group Lectures: Think alouds & difficulty factors assessment,

Educational Data Mining

Page 23: An Introduction to TuTalk: Developing Dialogue Agents for Learning Applications

Wednesday TuTalk Track

Track Lecture: Advanced TuTalk Dialogue Agents Discuss TuTalk server and its support tools Explore additional authoring features (e.g. looping, optional steps)

Project: Test and refine dialogue goals & implemented dialogues Project: Add more expected student responses & follow-ups Project: Test and refine additions Project: Create alternative ways of achieving dialogue goals &

subgoals, e.g. Version of dialogue for advanced student (e.g. agent does or summarizes

easy steps and scaffolds harder steps, ask for justifications) Version for less advanced student (e.g. agent scaffolds easy steps and

models the harder steps, agent explains justifications for steps) Group Lectures: Issues in transfer & learning, Cognitive principles in

tutor design Group Demos (in parallel): ML for building a cognitive tutor, ESL

demo

Page 24: An Introduction to TuTalk: Developing Dialogue Agents for Learning Applications

Thursday TuTalk Track

Project: Test latest dialogues and refine Project: Finalize dialogue agent

Final testing Set up an interface to demo agent for poster session Integrate with other tools that are triggers for dialogue

goals

Project: Prepare posters, presentations Lecture: Socio-cultural perspectives on learning

Page 25: An Introduction to TuTalk: Developing Dialogue Agents for Learning Applications

TuTalk Development Team

Authoring tools: Carolyn Rosé Yue Cui (Jenny) Rohit Kumar

Dialogue system & server: Pam Jordan Brian Hall (Moses) Michael Ringenberg

Page 26: An Introduction to TuTalk: Developing Dialogue Agents for Learning Applications

TuTalk Summer School Team

Pam Jordan (dialogue system behavior, dialogue management module)

Moses Hall (interface, integration, implementation of system modules)

Min Chi (experienced dialogue author)

Page 27: An Introduction to TuTalk: Developing Dialogue Agents for Learning Applications

Click to edit the title text formatMore info & software download:

http://andes2.lrdc.pitt.edu/[email protected]@pitt.edu

Page 28: An Introduction to TuTalk: Developing Dialogue Agents for Learning Applications

Click to edit the title text formatDemo snapshots

Page 29: An Introduction to TuTalk: Developing Dialogue Agents for Learning Applications

Authoring a dialogue with subdialogues

Page 30: An Introduction to TuTalk: Developing Dialogue Agents for Learning Applications

Authoring a subdialogue

Page 31: An Introduction to TuTalk: Developing Dialogue Agents for Learning Applications

Extending concept definitions

Page 32: An Introduction to TuTalk: Developing Dialogue Agents for Learning Applications

Previewing authored dialogues

Page 33: An Introduction to TuTalk: Developing Dialogue Agents for Learning Applications

Testing with dialogue agent server